Ranked data should be integral (-78, -5, 1, 3, 0, 42, etc.). If your original data is fractional (32.65, -21.2, etc.), OptiPath will convert each number to an integer rank. If the feature parameter Ranks = 1, all data (alphanumeric as well as numeric) will be converted to the single rank = 1 (the exception being blanks and zeroes, being interpreted as absences or unknowns according to the Earlier, Later, Blanks and Zeroes parameters respectively). Ranked data is often used to reflect a count or an ordinal position in a rank ordering of the values of a feature. Ranked data can be used to categorize data where the ordering of the categories is important. Depending upon the Metric used, OptiPath will try to preserve the order of the categories (smallest to largest or vice versa) in creating a seriation.
Ranked data can be specified in the Features table. The feature parameter Data can be used to specify that a feature should use ranked data. Right clicking on the column brings up a popup menu that allows you to set all features with one click.
Ranked data is usually associated with occurrence seriation (where a data value represents the number of times a feature appears for an artifact or discrete seriation (where the data values represent the ranked values or relative magnitudes of features for an artifact).
Ranked data is not appropriate for frequency seriation and shortest path seriation (where measured data is more appropriate ) nor for nominal seriation (where classed data is more appropriate).
For ranked data the feature parameter Ranks can take on the value 0, 1 or any integer greater than one. See Ranks. If the value of Ranks is 0, there is no limit to the number of ranks or classes the data might take on.
To see the effect on the raw data of setting various feature parameters, including the Data parameter, look at processed data in the Values table.